MagicMask:A Fast and High-fidelity Face Swapping Method Robust to Face Pose

Recent face-swapping methods excel under controlled conditions but often fail when presented<br/>with extreme facial poses. Diffusion-based approaches may be able to overcome these issues, but they still face significant computational costs. This paper introduces MagicMask, a novel faceswapping framework that robustly handles various poses in real time by fusing visual and geometric information. Our method incorporates explicit, identity-adapted geometric cues into the latent feature space via a multi-head attention mechanism. It employs an Adversarial Facial Silhouette Alignment (AFSA) loss to preserve detailed facial boundaries that are adapted to the source identity.<br/>Comprehensive experiments on multiple benchmarks demonstrate that MagicMask competes with<br/>state-of-the-art methods under standard conditions and significantly outperforms them in extreme pose scenarios.